© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16726
    Prev
    Next
    INDEX
    Explanations

    half of / half-century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stm
    -0.09
    ches
    -0.09
    ESH
    -0.09
    staking
    -0.09
    lä
    -0.09
     rebound
    -0.08
    Verdana
    -0.08
     Alley
    -0.08
     Teddy
    -0.08
     craft
    -0.08
    POSITIVE LOGITS
    å¾Ħ
    0.14
     dozen
    0.14
    -century
    0.13
    -hour
    0.13
    /full
    0.11
    court
    0.10
     hour
    0.10
    moon
    0.10
    teenth
    0.10
    ord
    0.09
    Activations Density 0.083%

    No Known Activations